Title :
Individual classification through autoregressive modelling of micro-doppler signatures
Author :
Garreau, Guillaume ; Nicolaou, Nicoletta ; Georgiou, Julius
Author_Institution :
Holistic Electron. Res. Lab., Univ. of Cyprus, Nicosia, Cyprus
Abstract :
This paper introduces the use of autoregressive modelling (AR) to characterize individual human gait signatures from micro-Doppler data. AR models are fitted to micro-Doppler data obtained while 6 subjects walk towards a custom-made ultrasonic transceiver module. The estimated AR coefficients capture individual movement characteristics. Such features can be used to identify different subjects quickly and with low computational cost. In the best configuration, average performance higher than 98% was obtained.
Keywords :
autoregressive processes; biomedical transducers; biomedical ultrasonics; gait analysis; transceivers; ultrasonic transducers; autoregressive coefficients; autoregressive modelling; human gait signatures; microDoppler signatures; ultrasonic transceiver module; Acoustics; Computational modeling; Data models; Humans; Legged locomotion; Radar; Transceivers; Micro-Doppler; autoregressive models; individual recognition; ultrasonic device;
Conference_Titel :
Biomedical Circuits and Systems Conference (BioCAS), 2012 IEEE
Conference_Location :
Hsinchu
Print_ISBN :
978-1-4673-2291-1
Electronic_ISBN :
978-1-4673-2292-8
DOI :
10.1109/BioCAS.2012.6418434
